Optimizing Cold Metal Transfer-Wire Arc Additive Manufacturing Parameters for Enhanced Mechanical Properties and Microstructure of ER5356 Aluminum Alloy Using Artificial Neural Network and Response Surface Methodology

Abstract

With significant benefits in resource consumption and production efficiency, wire arc additive manufacturing (WAAM) has become a critical method in manufacturing metal components. The goal of this research is to maximize bead width (BW) and bead height (BH) by optimizing the welding parameters current, voltage, and traverse speed in the gas metal arc welding (GMAW) cold metal transfer (CMT) process utilizing response surface methodology (RSM) and artificial neural networks (ANNs). Initially, ANNs were employed to predict bead geometry, demonstrating high predictive accuracy with R² values of 0.964 for BW and 0.9713 for BH. Employing Design Expert 13 software, predictive models were developed, revealing the relationships between these parameters and bead characteristics. Optimal parameters were identified as a current of 135 A, voltage of 16 V, and traverse speed of 40 cm/min, achieving a bead width of 5.8 mm and bead height of 3.65 mm. Microstructural analyses via x-ray diffraction (XRD) and scanning electron microscopy (SEM) highlighted significant variations, with distinct crystallographic orientations and micro-cracks observed across different sections of the Al5356 material. Electron backscatter diffraction (EBSD) further illustrated grain structure and orientation variations. Mechanical properties tests demonstrated that the bottom section exhibited the highest ultimate tensile stress (UTS) at 294.11 MPa and yield strength (YS) at 190.38 MPa. In contrast, the middle section had the highest hardness value at 74 HV. This research underscores the importance of optimizing WAAM parameters to enhance mechanical properties and microstructural integrity, providing valuable insights for future applications in additive manufacturing.